import torch
import gradio as gr
from PIL import Image, ImageDraw, ImageFont

# Use a pipeline as a high-level helper
from transformers import pipeline

# model_path = "../Models/models--facebook--detr-resnet-50/snapshots/1d5f47bd3bdd2c4bbfa585418ffe6da5028b4c0b"

object_detector = pipeline("object-detection", model="facebook/detr-resnet-50")

# object_detector = pipeline("object-detection", model=model_path)


def draw_bounding_boxes(image, detections, font_path=None, font_size=500):
    """
    Draws bounding boxes on the given image based on the detections.
    :param image: PIL.Image object
    :param detections: List of detection results, where each result is a dictionary containing
                       'score', 'label', and 'box' keys. 'box' itself is a dictionary with 'xmin',
                       'ymin', 'xmax', 'ymax' keys.
    :param font_path: Path to the TrueType font file to use for text.
    :param font_size: Size of the font to use for text.
    :return: PIL.Image object with bounding boxes drawn.
    """
    # Make a copy of the image to draw on
    draw_image = image.copy()
    draw = ImageDraw.Draw(draw_image)

    # Load custom font or default font if path not provided
    if font_path:
        font = ImageFont.truetype(font_path, font_size)
    else:
        # Use default font, increase font size with TTF font if necessary
        font = ImageFont.load_default()

    for detection in detections:
        box = detection['box']
        xmin = box['xmin']
        ymin = box['ymin']
        xmax = box['xmax']
        ymax = box['ymax']

        # Draw the bounding box
        draw.rectangle([(xmin, ymin), (xmax, ymax)], outline="red", width=3)

        # Optionally, draw the label and score
        label = detection['label']
        score = detection['score']
        text = f"{label} {score:.2f}"

        # Draw text with background rectangle for visibility
        if font_path:
            text_size = draw.textbbox((xmin, ymin), text, font=font)
        else:
            text_size = draw.textbbox((xmin, ymin), text)

        draw.rectangle([(text_size[0], text_size[1]), (text_size[2], text_size[3])], fill="red")
        draw.text((xmin, ymin), text, fill="white", font=font)

    return draw_image


# for text output
# raw_image = Image.open("../Files/cat.jpg")
# output = object_detector(raw_image)
# print(output)


# Function for object detection and bounding box drawing
def detect_object(image):
    raw_image = image
    output = object_detector(raw_image)
    processed_image = draw_bounding_boxes(raw_image, output)
    return processed_image


demo = gr.Interface(
    fn=detect_object,
    inputs=[gr.Image(label="Select Image", type="pil")],
    outputs=[gr.Image(label="Processed Image", type="pil")],
    title="Project 05: Object Detector",
    description="As understood from the title, if not already, this application will detect objects in your image"
)

demo.launch()